Skip to content

Evidence tables

Sharpe ratio, mean ± sd over 5 seeds [min, max]

Agent Reported Share env + turbulence rule Share env, no rule Benchmark paper-2021
DDPG 1.38 1.16 ± 0.19 [0.92, 1.43] 1.06 ± 0.18 [0.80, 1.24] 0.70 ± 0.17 [0.57, 0.97]
TD3 1.37 1.10 ± 0.34 [0.57, 1.37] 1.00 ± 0.30 [0.53, 1.37] 0.70 ± 0.21 [0.43, 1.01]
SAC 1.33 1.23 ± 0.13 [1.07, 1.42] 1.23 ± 0.18 [1.01, 1.49] 0.66 ± 0.26 [0.19, 0.82]
PPO 1.09 1.17 ± 0.21 [0.80, 1.32] 0.95 ± 0.21 [0.74, 1.21] 0.98 ± 0.04 [0.93, 1.02]
A2C 0.82 1.09 ± 0.15 [0.91, 1.27] 0.97 ± 0.15 [0.80, 1.16] 1.03 ± 0.01 [1.01, 1.05]
LSTM forecast 1.19 – – 0.75 ± 0.29 [0.45, 1.08]
1/N buy and hold – 1.10 1.10 1.11

Annual return, mean ± sd over 5 seeds [min, max]

Agent Reported Share env + turbulence rule Share env, no rule Benchmark paper-2021
DDPG 55.51% 24.6% ± 5.9 [15.9%, 30.4%] 30.6% ± 8.3 [18.5%, 40.5%] 16.2% ± 5.4 [12.0%, 25.0%]
TD3 42.00% 23.3% ± 9.4 [8.8%, 31.3%] 28.7% ± 12.3 [10.8%, 44.9%] 15.7% ± 5.8 [8.5%, 24.4%]
SAC 38.95% 25.1% ± 2.5 [21.1%, 27.8%] 38.5% ± 7.0 [27.8%, 46.0%] 15.1% ± 7.6 [1.6%, 19.7%]
PPO 27.89% 16.0% ± 4.7 [10.6%, 22.3%] 25.3% ± 7.9 [15.6%, 33.3%] 23.9% ± 1.2 [22.3%, 25.4%]
A2C 20.47% 21.5% ± 5.1 [16.5%, 28.2%] 26.0% ± 6.5 [19.0%, 35.4%] 25.1% ± 0.4 [24.7%, 25.8%]
LSTM forecast 16.99% – – 17.9% ± 9.5 [9.1%, 28.3%]
1/N buy and hold – 29.7% 29.7% 29.9%

Maximum drawdown, mean over 5 seeds [worst, best]

Agent Reported Share env + turbulence rule Share env, no rule Benchmark paper-2021
DDPG -33.52% -18.0% [-18.6%, -17.4%] -27.8% [-30.8%, -25.7%] -29.3% [-31.7%, -27.4%]
TD3 -25.24% -19.0% [-20.2%, -17.5%] -28.2% [-32.7%, -25.0%] -29.3% [-33.7%, -26.5%]
SAC -24.19% -17.7% [-21.8%, -14.8%] -27.0% [-32.2%, -22.5%] -30.2% [-33.7%, -28.1%]
PPO -25.33% -9.2% [-11.7%, -6.7%] -27.4% [-32.0%, -25.3%] -28.1% [-28.6%, -27.6%]
A2C -31.11% -17.2% [-18.9%, -14.5%] -29.0% [-31.2%, -26.5%] -28.2% [-28.3%, -28.0%]
LSTM forecast −9.57% – – -26.5% [-28.8%, -23.8%]
1/N buy and hold – – – -29.4%

Sharpe against 1/N, seed-averaged returns (one-sided paired stationary bootstrap)

Share env (A, B): from paper-2021-share-env-equity.json, alpha, beta and the Newey-West t of the seed-averaged daily returns. Benchmark (C): alpha, beta and t as in leaderboard/LEADERBOARD.md (per-seed values averaged). 'Seeds above' counts seeds whose own Sharpe exceeds that setup's 1/N Sharpe.

Setup Agent Sharpe of seed-avg returns ΔSharpe vs 1/N p Alpha Alpha t (HAC) Beta Seeds above 1/N
Share env + turbulence rule DDPG 1.22 +0.12 0.320 7.4% 0.9 0.56 3/5
Share env + turbulence rule TD3 1.20 +0.09 0.328 6.4% 0.9 0.55 3/5
Share env + turbulence rule SAC 1.33 +0.22 0.218 8.9% 1.2 0.52 4/5
Share env + turbulence rule PPO 1.26 +0.15 0.339 6.7% 1.1 0.30 4/5
Share env + turbulence rule A2C 1.14 +0.04 0.398 5.4% 0.7 0.54 2/5
Share env, no rule DDPG 1.11 +0.00 0.496 1.2% 0.3 1.00 3/5
Share env, no rule TD3 1.06 -0.04 0.654 -0.2% -0.0 0.99 1/5
Share env, no rule SAC 1.32 +0.22 0.133 7.5% 1.6 1.00 4/5
Share env, no rule PPO 1.00 -0.11 0.713 -2.0% -0.4 0.95 1/5
Share env, no rule A2C 0.99 -0.11 0.792 -2.3% -0.6 0.98 1/5
Benchmark paper-2021 DDPG 0.71 -0.40 0.985 -9.9% -2.2 0.95 0/5
Benchmark paper-2021 TD3 0.71 -0.40 0.977 -9.4% -1.7 0.91 0/5
Benchmark paper-2021 SAC 0.68 -0.43 0.998 -10.8% -2.2 0.95 0/5
Benchmark paper-2021 PPO 0.98 -0.13 0.898 -2.9% -1.2 0.92 0/5
Benchmark paper-2021 A2C 1.03 -0.08 0.825 -1.8% -0.8 0.92 0/5
Benchmark paper-2021 LSTM forecast 0.84 -0.27 0.831 -4.4% -0.5 0.81 0/5

Sessions with unchanged equity (|daily return| < 1e-9)

Setting Runs Runs with no such session Distinct sets of such sessions Sessions
Share env + turbulence rule 25 0 1 2020-03-17, 2020-03-20, 2020-03-23, 2020-03-24, 2020-03-25
Share env, no rule 25 25 1 –

Per-seed Sharpe ratio

Setup Agent Seed 0 Seed 1 Seed 2 Seed 3 Seed 4
Share env + turbulence rule DDPG 1.43 1.08 1.18 1.20 0.92
Share env + turbulence rule TD3 1.37 0.98 0.57 1.28 1.31
Share env + turbulence rule SAC 1.42 1.07 1.27 1.21 1.20
Share env + turbulence rule PPO 1.32 1.19 0.80 1.32 1.21
Share env + turbulence rule A2C 1.27 1.09 1.20 1.00 0.91
Share env, no rule DDPG 1.24 0.98 1.11 1.18 0.80
Share env, no rule TD3 1.37 0.96 0.53 1.05 1.07
Share env, no rule SAC 1.49 1.01 1.33 1.17 1.14
Share env, no rule PPO 1.09 0.76 0.74 0.94 1.21
Share env, no rule A2C 1.16 0.98 1.03 0.80 0.85
Benchmark paper-2021 DDPG 0.57 0.61 0.97 0.77 0.59
Benchmark paper-2021 TD3 0.72 1.01 0.61 0.72 0.43
Benchmark paper-2021 SAC 0.19 0.82 0.71 0.77 0.80
Benchmark paper-2021 PPO 0.93 1.02 0.98 0.97 1.01
Benchmark paper-2021 A2C 1.02 1.02 1.05 1.01 1.03
Benchmark paper-2021 LSTM forecast 0.63 0.56 1.08 1.05 0.45

Per-seed annual return

Setup Agent Seed 0 Seed 1 Seed 2 Seed 3 Seed 4
Share env + turbulence rule DDPG 30.4% 21.9% 25.7% 29.0% 15.9%
Share env + turbulence rule TD3 31.3% 18.8% 8.8% 28.9% 28.7%
Share env + turbulence rule SAC 27.8% 21.1% 25.3% 26.2% 25.1%
Share env + turbulence rule PPO 22.3% 12.2% 10.6% 17.3% 17.5%
Share env + turbulence rule A2C 28.2% 21.9% 24.5% 16.5% 16.6%
Share env, no rule DDPG 35.2% 27.1% 31.8% 40.5% 18.5%
Share env, no rule TD3 44.9% 25.9% 10.8% 29.9% 32.3%
Share env, no rule SAC 46.0% 27.8% 42.3% 40.6% 35.8%
Share env, no rule PPO 32.8% 15.6% 19.3% 25.3% 33.3%
Share env, no rule A2C 35.4% 26.3% 28.1% 19.0% 21.0%
Benchmark paper-2021 DDPG 12.0% 12.3% 25.0% 17.6% 14.0%
Benchmark paper-2021 TD3 16.1% 24.4% 13.7% 15.9% 8.5%
Benchmark paper-2021 SAC 1.6% 19.5% 17.3% 17.3% 19.7%
Benchmark paper-2021 PPO 22.3% 25.4% 23.6% 23.5% 24.5%
Benchmark paper-2021 A2C 24.9% 25.0% 25.8% 24.7% 25.3%

Verdict by setup (same rule everywhere)

Claim Share env + turbulence rule Share env, no rule Benchmark paper-2021
ddpg-annual-return ✗ ✗ ✗
ddpg-sharpe ◐ ✗ ✗
td3-sharpe ◐ ◐ ✗
sac-sharpe ◐ ◐ ✗
ppo-sharpe ◐ ◐ ✗
a2c-sharpe ◐ ◐ ◐